Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Pakistani topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    桓
    -0.07
    搓
    -0.07
    ULE
    -0.07
     "":↵
    -0.07
    _decay
    -0.07
    atra
    -0.07
    FXML
    -0.06
     ante
    -0.06
    CALE
    -0.06
     yaşama
    -0.06
    POSITIVE LOGITS
     Hor
    0.07
    sizes
    0.07
     '.',
    0.07
     Ber
    0.07
     Elliot
    0.07
    교회
    0.06
     Quick
    0.06
     Jet
    0.06
     Bread
    0.06
    בלה
    0.06
    Act Density 0.056%

    No Known Activations